Predictive diagnosis of diabetes based on multiple linear regression

Boxing Liu

doi:10.1117/12.2669013

24 March 2023 Predictive diagnosis of diabetes based on multiple linear regression

Boxing Liu

Proceedings Volume 12611, Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022); 1261147 (2023) https://doi.org/10.1117/12.2669013
Event: International Conference on Biological Engineering and Medical Science (ICBioMed2022), 2022, Oxford, United Kingdom

Abstract

The number of persons with diabetes has more than doubled worldwide during the past 20 years. Therefore, the primary subject of our study is the influence of possible factors. In this paper, we first removed the abnormal data from the dataset, and then excluded the categories with small predictive factors (P-value<0.05) for diabetes outcome by analysis of variance with P-values, and then used the multiple linear regression model to predict the outcome of diabetes prediction, which achieved an accuracy of 72%. Finally, the receiver operating characteristic curve (ROC) curve was used to evaluate the effectiveness of the model in prediction. The experimental results show that the prediction of diabetes using multiple linear regression can achieve a high accuracy when there are multiple influences on the data.

Citation Download Citation

Boxing Liu "Predictive diagnosis of diabetes based on multiple linear regression", Proc. SPIE 12611, Second International Conference on Biological Engineering and Medical Science (ICBioMed 2022), 1261147 (24 March 2023); https://doi.org/10.1117/12.2669013

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available